pykan
pykan copied to clipboard
KindXiaoming
Kolmogorov Arnold Networks
The statement "model (dataset ['train input '])" in the "hellokan. ipynb" encountered an error while running: RuntimeError: Expected all tensors to be on the same device, but found at least...
Hello, In the past, I tried to get the formula of the differential scattering cross section of e+e- to mu+mu- scattering in quantum electrodynamics (or other process in other theory)...
Thanks for your great work. It paves another way different from MLP. However, I find that the authors try to overload the "train()" function of the "KAN" class, which is...
Congratulations on Ziming for the amazing and great work.Is there any TF version of KANs ?
"My results are not efficient with unbalanced data."
When I run **hellokan.ipynb**, a **runtime error** occurs due to **Nan**. I didn't change any Settings, just ran it, repeated it 10 times and still got a runtime error. ```...
in line 758, above train() add plt.savefig(f'{folder}/'+file_name) def plot(self, folder="./figures", beta=3, mask=False, mode="supervised", scale=0.5, tick=False, sample=False, in_vars=None, out_vars=None, title=None, file_name="file"): and in def you should add file_name="file" after title def...
Much research has been done on subject KAN in GitHub, and much has been discovered. Thanks a million, You did a good job! I research on your Example_1_function_fitting.ipynb from KAN...
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
Code: from kan import KAN import matplotlib.pyplot as plt from sklearn.datasets import make_moons import torch import numpy as np dataset = {} train_input, train_label = make_moons(n_samples=1000, shuffle=True, noise=0.1, random_state=None) test_input,...
